Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math or "all," greeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তরে
    0.73
     [...]
    0.73
     …,
    0.69
    ...,
    0.68
     Palace
    0.66
    …,
    0.65
     Vara
    0.65
     [...
    0.64
     }=\
    0.64
     Struct
    0.63
    POSITIVE LOGITS
    丶
    0.92
    IT
    0.90
    आईटी
    0.90
    lems
    0.89
     IT
    0.88
    IFICATE
    0.86
    circ
    0.85
    henius
    0.84
    ាម
    0.83
    amad
    0.83
    Act Density 1.574%

    No Known Activations